Grad-CAM Enhanced Explainable Deep Learning for Multi-Class Lung Cancer Classification Using DE-SAMNet Model

Basit Öğe Kaydı
dc.contributor.authorKilic, Murat
dc.contributor.authorBiyikli, Merve
dc.contributor.authorYelman, Abdulkadir
dc.contributor.authorFirat, Huseyin
dc.contributor.authorUzen, Huseyin
dc.contributor.authorCicek, Ipek Balikci
dc.contributor.authorSengur, Abdulkadir
dc.date.accessioned2026-04-04T13:31:09Z
dc.date.available2026-04-04T13:31:09Z
dc.date.issued2026
dc.departmentİnönü Üniversitesi
dc.description.abstractBackground/Objectives: Lung cancer (LC) is the leading cause of cancer-related mortality worldwide, making early and accurate diagnosis crucial for improving patient outcomes. Although chest computed tomography (CT) enables detailed assessment of lung abnormalities, manual interpretation is time-consuming, requires expert expertise, and is prone to diagnostic variability. To address these challenges, this study proposes DE-SAMNet, a hybrid deep learning framework for automated multi-class LC classification from CT scans. Methods: The model integrates two pre-trained convolutional neural networks-DenseNet121 and EfficientNetB0-operating in parallel to extract complementary multi-scale features. A Spatial Attention Module (SAM) is applied to each feature stream to emphasize clinically important regions. Final classification is performed through a compact fusion mechanism involving global average pooling, batch normalization, and a fully connected layer. DE-SAMNet was evaluated on two datasets: a public dataset (IQ-OTH/NCCD) with benign, malignant, and normal cases, and a private clinical dataset including benign, malignant, cystic, and healthy cases. Results: On the public dataset, the model achieved a 99.00% F1-score, 98.41% recall, 99.64% precision, and 99.54% accuracy. On the private dataset, it obtained 95.96% accuracy, 95.99% precision, 96.04% F1-score, and 96.21% recall, outperforming existing approaches. To enhance reliability, explainable AI (XAI) techniques such as Grad-CAM were used to visualize the model's decision rationale. The resulting heatmaps effectively highlight lesion-specific regions, offering transparency and supporting clinical interpretability. Conclusions: This explainability strengthens trust in automated predictions and demonstrates the clinical potential of the proposed system. Overall, DE-SAMNet delivers a highly accurate and interpretable solution for early LC detection.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TBIdot;TAK) [125E062]
dc.description.sponsorshipThis study was supported by the Scientific and Technological Research Council of Turkey (TUB & Idot;TAK) through the 1001 Scientific and Technological Research Projects Funding Program (Project No: 125E062).
dc.identifier.doi10.3390/diagnostics16050757
dc.identifier.issn2075-4418
dc.identifier.issue5
dc.identifier.pmid41828033
dc.identifier.scopus2-s2.0-105032689347
dc.identifier.scopusqualityQ2
dc.identifier.urihttps://doi.org/10.3390/diagnostics16050757
dc.identifier.urihttps://hdl.handle.net/11616/108598
dc.identifier.volume16
dc.identifier.wosWOS:001713906900001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherMdpi
dc.relation.ispartofDiagnostics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250329
dc.subjectlung cancer
dc.subjectclassification
dc.subjectdensenet121
dc.subjectefficientnetb0
dc.subjectspatial attention module
dc.titleGrad-CAM Enhanced Explainable Deep Learning for Multi-Class Lung Cancer Classification Using DE-SAMNet Model
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu